Annual Report Research Institute in Economics & Econometrics RESEARCH INSTITUTE OF THE FACULTY OF ECONOMICS & ECONOMETRICS

163  Download (0)

Full text

(1)

Annual Report

2004

Research Institute in Economics & Econometrics

RESEARCH INSTITUTE OF THE FACULTY OF ECONOMICS & ECONOMETRICS UNIVERSITEIT VAN AMSTERDAM

(2)

RESAM, Research institute in EconomicS & econometrics AmsterdaM

Universiteit van Amsterdam Roetersstraat 11

NL-1018 WB Amsterdam Director : Prof.dr. H. Oosterbeek Office: Drs B.C. Bouten

T: +31-20-5255261 F: +31-20-5254026 E: resam-fee@uva.nl

(3)

CONTENTS

PART A – THE RESEARCH INSTITUTE

Chapter 1 Institutional review 3

1.1 Mission statement 3

1.2 Allocating resources 3

1.3 Strategy and policy 5

Chapter 2 Input 7

2.1 Researchers and other personnel 7

2.2 Resources, funding and facilities 9

Chapter 3 Current state of affairs 12

3.1 Processes in research, internal and external collaboration 12

3.2 Academic reputation 13

3.3 Overview of results 15

Chapter 4 Analysis, perspectives and expectations for the institute 17

4.1 SWOT Director RESAM 17

4.2 Assessment Council of Programme Leaders 17

PART B – RESEARCH PROGRAMMES

UvA-Econometrics prof.dr. J.F. Kiviet 21

Operations Research prof.dr. N.M. van Dijk 33

Equilibrium, Expectations & Dynamics prof.dr. C.H. Hommes 41

Actuarial Science prof.dr. R. Kaas 51

Other research quantitative economics 63

The Transformation of Europe prof.dr. R.M.W.J. Beetsma 65

Human Capital prof.dr. J. Hartog 85

History & Methodology of Economics prof.dr. J.B. Davis & dr. G.A.T.M. Reuten 109 Experimental and Political Economics prof.dr. F.A.A.M. van Winden 121

Other research economics 133

SEO Amsterdam Economics prof.dr. C.N. Teulings 135

APPENDICES

Appendix I List of persons, committees and addresses 151

(4)
(5)

A

The Research Institute

(6)
(7)

3

CHAPTER 1: INSTITUTIONAL REVIEW

1.1. MISSION STATEMENT

RESAM has the following mission statement.

* RESAM aims for research results that significantly improve our understanding of the operation of economic systems, the behaviour of agents in the economy, and the effects of economic policies.

* RESAM facilitates and promotes research by faculty members of the FEE to foster the academic ideal of intertwined university research and teaching.

RESAM (Research in EconomicS and econometrics AmsterdaM), is one of the two research institutes of the Faculty of Economics & Econometrics; the other being the research institute of the Amsterdam graduate Business School (AgBS-RI). It was established in 1998 after the MUB (Wet Modernisering Universitair Bestuur (law on the modernizing of university management)) came in effect and it covers the wide area of economics and econometrics as can be seen from the names of the two Departments that employs its researchers: Algemene Economie (AE, economics) and Kwantitatieve Economie (KE, Quantitative Economics).

Research is organised in Research Programmes, directed by experts with core positions in the curriculum. Stimulating research that significantly improves our understanding of the economy is meant as a focus on fundamental research. In many cases, the inspiration for research questions derives from practical problems in business and society as well as from pressing problems for government policies, as is only natural for a social science. But the research results should primarily be reported to the international academic community and assessed against the quality standards that apply there. Such permanent quality assessment feeds back into the quality of teaching and of advice given to business and the government. Contributions to public debates should be a consequence of developing reliable knowledge about the economy rather than a primary goal.

RESAM closely co-operates with the Tinbergen Institute, where many of RESAM’s researchers are appointed as fellow. The Tinbergen Institute also acts as the graduate school for RESAM Ph.D. students.

1.2. ALLOCATING RESOURCES

The total faculty time budget available in the FEE, after deducting time for administrative positions (department chairpersons, curriculum co-ordinators, institute directors), is divided between the two research Institutes, RESAM and AgBS-RI. In principle time is equally allocated to teaching and to research. Departments are compensated by the research institute (RESAM for AE and KE) and the teaching institute (OWI) for research and teaching tasks the department provides. Faculty members in the AE and KE departments are annually assigned time for research on the basis of their publication records in the past three years. In this way RESAM tries to stimulate faculty to increase the quality and quantity of their output.

(8)

Publications are graded by quality level of the outlet. For journals, RESAM distinguishes

· A: excellent, international top level

Publications in A level journals set directions for research, by approach and by method. They select topics and set standards for analytical and methodological level.

· B: good international level

Publications in B level journals meet high analytic and methodological standards but have far less influence on direction and standards for future research.

· C: international refereed journals

These journals satisfy the minimum norm of aiming for an international audience, applying blind refereeing, and publish in an accessible language. Analytical and methodological standards satisfy a generally accepted minimum level.

· D: other, non-refereed and refereed

RESAM has drawn up a list of rankings of publication outlets (journals, publishing houses, conference proceedings, see the RESAM website www.fee.uva.nl/resam). The minimum norm for adequate research performance is formulated as 100 points over the past three years. An A-level publication counts for 100 points, a B-level for 50 points, and a C-level for 25 points in 2000 and 2001. Individual authors of a publication with n authors each get a share of 2/(1+n) points of the publication. The weight for C-level publications is being linearly reduced in three steps, with a resulting weight of zero for research published in 2004. The new system has become operational for the research time assignment of the calendar year 2004 which has been calculated in 2003 on the basis

(9)

of points earned by output published in 2000-2001-2002, for in 2002 a C publication counted for 16.67 points (2/3*25) for the first time. The system will be fully implemented when research time is allocated for 2008, on the basis of results from 2004-2005-2006, three consecutive years in which a C publication does not yield points. Research time assigned to individuals is related to publication points over the past three years as follows:

100 or more : 0.5 fte

50-99 : 0.25 fte

1-49 : 0.125 fte

0 : 0 fte

For faculty members with part-time positions, norms and research time are adjusted proportionally. Fellows of the Tinbergen Institute, the graduate research school in which UvA, EUR and VU co-operate, have a five year protection period of their research time at the maximum of 0.5 of their working hours. Admission as TI Fellow is based on A- and B-level publications only (TI has its own grading of publications). New appointees are allotted the maximum research time for a period of three years.

RESAM stimulates concentration of the faculty’s research in Research Programmes also by other means (such as an annual amount for conference visits and other academic activities to the research programmes).

At least once a year RESAM hosts a meeting of the Council of Programme Leaders to discuss the results of the past year and plans for the future. The Director of the research institute, furthermore, has contact with the Dean on a regular basis.

1.3. STRATEGY AND POLICY

After the VSNU Quality Assessment of Research in 1995, the Faculty started a process of realigning its research efforts by reducing the amount of research programmes. Before this assessment there were 25 programmes but in the next Quality Assessment (2001) only 14 programmes were submitted for evaluation. Several programmes in economics and econometrics were merged while research in the fields of marketing and management were discontinued. Thereafter the faculty has successfully focused its research programme even further. In 2002 the AgBS-RI was established to stimulate research in business studies (with the three former RESAM programmes of Accounting, Organisations and Society, Corporate Finance and Financial Systems and Information Management). RESAM continued with eight1 research programme plus the SEO.2

RESAM aims to reach its goals by organising, stimulating and monitoring Research Programmes. Annually, Programme performance is assessed. Means are allocated to Programmes based on performance. Research coverage is not directed and controlled by the Faculties management, but develops in an open competitive environment. General policy issues are discussed at the annual convocation of the Council of Programme Directors.

1 In 2005 a new research programme will be established: ENCORE/IO. This small programme conducts research in the field of Industrial

Organization, with an emphasis on issues of competition and regulation.

2 The SEO has a rather special status. It is a foundation for commercial contract research which seeks to benefit from interaction with

academic research. By special agreement SEO is compensated for publication in the international academic community and is also considered as one of RESAMs research programmes.

(10)

Box 1: Research Highlight: Harro Maas. Representing Economic Phenomena

Over the past years research in history and methodology of economics at our faculty has focussed importantly on modelling and measurement practices in economics. Margaret Morrison and Mary Morgan’s Models as Mediators (CUP, 1999) was the first collection of essays in which modelling practices in economics and natural sciences were compared and analysed. It comprised, among others, work of Marcel Boumans, Geert Reuten and our close collaborators at LSE at the Centre for Philosophy of Natural and Social Sciences (CPNSS), and already has become a standard reference for philosophers and methodologists of the natural and social sciences.

An important message of this collection of essays is that models function as instruments that serve representational and measuring functions both at once, much like the thermometer serves as a representation of temperature by measuring

its value. This simple insight underlies research of Marcel Boumans and of myself over the past years, research that has culminated recently in the publication of two books, Marcel’s How Economists Model the World into Numbers (Routledge, 2005), and my own William Stanley Jevons and the Making of Modern Economics (CUP, May 2005). Though conceptually there are many points of commonality between the books of Marcel and myself, for the purpose of this highlight, I will limit myself to my own book.

My book is a thoroughly reworked version of my thesis (2001), that greatly benefited from an NWO supported three month visit at Clare Hall, Cambridge. In it, I explore the intellectual and social resources Jevons drew upon to revolutionize economic theory and method. The book delves into the different styles of scientific investigation that were current in Victorian England. These styles can be roughly characterised by the different stances that were taken on issues like the relation of (passive field) observations to (active laboratory) experiments, the relation of mind to matter, and its implications for the notorious issue of free will, and - perhaps most importantly - the relation of material instruments to symbolic means of analysis. To summarize a much longer history briefly: Jevons's revolution in economics is better understood against the background of the newly emerging experimental methods in physiology and psychophysics, than as a mathematical rendition of Bentham's calculus of pleasure and pain. Jevons clearly dismissed introspection as unscientific and aimed to show to economists how means of representation of economic phenomena current in the other sciences could be applied to economics as well. His use of mathematics makes more sense once we understand the obsession of Victorians like Charles Babbage and Augustus De Morgan with machinery and symbolic algebra - this obsession feeds Jevons's own work in meteorology and symbolic logic as well, but it was completely incomprehensible to the towering Victorian philosopher and economist John Stuart Mill who heavily relied on introspection as the alpha and omega of the moral sciences, including political economy. However, it should be emphasized that representational practices create (economic) phenomena as well, as the business cycle first became a (still disputed) phenomena, once it was graphed, and similar holds for Jevons's accomplishments. In my present research I explore the relation between concept formation and representational practices in more detail for the early and late twentieth century. I am interested in particular in how recent boundary crossings between the neurological sciences and economics transform the conceptual and visualising tools of economics, and how these transformations change the notion of evidence for theories. I pursue this research in close cooperation with the interdisciplinary research project "The History of Scientific Observation" of the Max Planck Institut für Wissenschaftsgeschichte at Berlin, and with the Leverhulme Trust funded research project at LSE Travelling Facts. As for our own group, it feeds into our current interest in the vagaries of the notion of rationality in twentieth century economics.

(11)

CHAPTER 2: INPUT

Personnel policy and human resource management is the domain of the department chair. Although, using the system to allocate research time described above, RESAM encourages the department to hire good researchers and to stimulate faculty to increase the quality and quantity of academic publications, it cannot exert direct influence on personnel policy.

2.1. RESEARCHERS AND OTHER PERSONNEL

The tables below give some information on RESAM faculty. Table 1 shows that between 2001 and 2003 total research capacity has expanded. This development was almost entirely due to increases in the so-called second flow of funds. In 2004 we experienced reductions in both first and second flow capacity; this was only partially compensated by an increase in third flow funding. Table 2 shows that trends differ somewhat across research groups.

Most faculty are in the ranks of professor and Ph.D. students. The number of post-docs has increased substantially, to 20, in 2002 and 19 in 2003. In 2000 only 11 postdocs worked at the FEE and their numbers were even less in the years before. In 2004 their number has decreased sharply again and only 12 postdocs remained at the FEE.

Table 1: Research Staff at institutional and programme level

INPUT RESAM 2004 fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 21.44 24.12 24.03 22.75

WP 2 (second flow of funds, excl. Ph.D.'s) 7.60 12.75 14.90 10.43

WP 3 (third flow of funds, excl. Ph.D.'s) 26.67 26.18 26.33 32.47

Ph.D. students 15.95 17.28 18.81 18.68

Total Research staff 71.66 80.33 84.07 84.33

Support staff RESAM (bureau) 0.60 0.60 0.60 0.60

Total Staff 72.26 80.93 84.67 84.93

UvA-Econometrics fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 3.96 3.73 4.14 3.35

WP 2 (second flow of funds, excl. Ph.D.'s) 0.50 1.75 1.80 0.90

WP 3 (third flow of funds, excl. Ph.D.'s) 0.00 0.00 0.00 0.00

Ph.D. students 1.40 1.15 1.80 2.37

Total Research staff 5.86 6.63 7.74 6.62

Operations Research fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 1.66 1.50 2.01 2.45

WP 2 (second flow of funds, excl. Ph.D.'s) 0.00 0.00 0.00 0.00

WP 3 (third flow of funds, excl. Ph.D.'s) 0.00 0.00 0.00 0.00

Ph.D. students 0.00 0.15 0.80 1.08

Total Research staff 1.66 1.65 2.81 3.53 Equilibrium, Expecatations & Dynamics fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 1.42 1.71 1.76 2.50

WP 2 (second flow of funds, excl. Ph.D.'s) 2.40 2.86 2.35 1.40

WP 3 (third flow of funds, excl. Ph.D.'s) 0.00 0.00 0.00 0.00

Ph.D. students 2.80 2.90 3.80 2.60

(12)

Actuarial Science fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 0.95 0.79 1.26 0.88

WP 2 (second flow of funds, excl. Ph.D.'s) 0.00 0.65 0.80 0.97

WP 3 (third flow of funds, excl. Ph.D.'s) 0.27 0.27 0.37 0.46

Ph.D. students 0.20 0.82 0.96 1.01

Total Research staff 1.42 2.53 3.39 3.32

The Transformation of Europe fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 4.62 5.13 4.27 3.97

WP 2 (second flow of funds, excl. Ph.D.'s) 0.00 0.00 1.26 0.10

WP 3 (third flow of funds, excl. Ph.D.'s) 0.10 0.11 0.11 0.94

Ph.D. students 2.46 2.41 2.85 2.97

Total Research staff 7.18 7.65 8.49 7.98

Human Capital fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 4.51 5.66 4.59 4.27

WP 2 (second flow of funds, excl. Ph.D.'s) 4.40 6.69 7.89 4.41

WP 3 (third flow of funds, excl. Ph.D.'s) 0.53 0.90 1.04 2.18

Ph.D. students 4.11 5.65 5.35 4.05

Total Research staff 13.55 18.90 18.87 14.91

History & Methodology of Economics fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 1.72 1.72 1.65 1.70

WP 2 (second flow of funds, excl. Ph.D.'s) 0.00 0.00 0.00 0.42

WP 3 (third flow of funds, excl. Ph.D.'s) 0.00 0.00 0.11 0.11

Ph.D. students 1.33 0.85 0.00 0.50

Total Research staff 3.05 2.57 1.76 2.73

Experimental & Political Economcis fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 2.60 3.88 4.35 3.11

WP 2 (second flow of funds, excl. Ph.D.'s) 0.30 0.80 0.80 2.23

WP 3 (third flow of funds, excl. Ph.D.'s) 1.07 0.20 0.00 0.04

Ph.D. students 2.65 2.35 2.45 3.30

Total Research staff 6.62 7.23 7.60 8.68

SEO fte 2001 2002 2003 2004

WP 1 (first flow of funds, excl. Ph.D.'s) 0.00 0.00 0.00 0.00

WP 2 (second flow of funds, excl. Ph.D.'s) 0.00 0.00 0.00 0.00

WP 3 (third flow of funds, excl. Ph.D.'s) 24.70 24.70 24.70 28.74

Ph.D. students 1.00 1.00 0.80 0.80

(13)

Table 2: Ranks at programme level

* hgl=professor, uhd=associate professor, ud=assistant professor, oz=researchers, pdoc=postdoctoral fellow

2.2. RESOURCES, FUNDING AND FACILITIES

In 2004 the second research institute of the FEE, AgBS-RI, formally established in 2002, was financially separated from RESAM and received its own funding. This explains the rather large differences between 2004 and the previous two years. Actual incomes (realisation) were substantially higher than expected (budget) primarily due to the fact that RESAM has been very successful in attracting external funding in 2004.

Table 3: Budget 2004 RESAM

As can be seen in table 4 only a very small part of RESAM funds is allocated to non-staff cost centres. Most of this non-staff funding goes to the Tinbergen Institute where it is used to cover the expenses of courses for Ph.D. students and is used to organize seminars for fellows.

Besides allocating funds to fixed cost-centres to meet obligations made in the past, the remainder of RESAM non-staff funds is distributed over the research programmes. This is done on the basis of the size of the programme (fte). Programme leaders are free to use money for any research related activities of programme members, such as visiting conferences, conducting experiments and collecting data.

Research programme

# fte # fte # fte # fte # fte # fte # fte # fte

UvA- Econometrics 4 1.61 3 1.30 3 1.24 - - 3 0.97 5 1.50 - - 18 6.62 Operations research 2 0.65 1 0.39 3 1.41 - - - - 2 1.08 - - 8 3.53 Equilibrium, expectations & dynamics 1 0.50 1 0.50 3 1.50 - - 2 1.40 5 2.60 - - 12 6.50 Actuarial science 5 0.99 1 0.00 1 0.25 2 0.10 1 0.47 3 1.01 1 0.50 14 3.32 Other research quantitative economics - - 1 0.30 3 0.13 - - - 4 0.43 The Transformation of Europe 7 1.83 2 0.73 4 1.39 2 0.10 1 0.83 7 2.97 11 0.13 34 7.98 Human Capital 6 2.86 3 1.17 5 1.48 4 1.75 4 3.60 8 4.05 8 0.00 38 14.91 Methodology & History of Economics 4 0.51 2 0.90 1 0.40 - - 1 0.42 1 0.50 2 0.00 11 2.73 Experimental & political economics 5 2.71 1 0.80 2 0.64 3 1.19 - - 8 3.30 5 0.04 24 8.68 Other research economics - - - 4 0.09 4 0.09 Foundation for economic research 4 2.43 - - - - 31 26.31 - - 2 0.80 - - 37 29.54

Total 38 14.09 15 6.09 25 8.44 42 29.45 12 7.69 41 17.81 31 0.76 204 84.33

Total

Oz Pdoc Ph.D.

Hgl Uhd Ud Guest

in M€ 2004* 2003 2002

Budget Realisation Realisation Realisation Income Government Grants 3.8 4.2 5.3 6.0 External sources 1.0 1.6 1.7 0.9 total 4.8 5.8 7.0 6.9 Expenditures academic staff 3.7 3.8 5.5 5.0 administrative staff 0.8 0.6 0.7 0.6 other 0.1 0.2 0.1 0.1 personnel (pl) 4.4 4.5 6.3 5.7 other (non-staff) 0.5 1.1 1.4 1.0 total 4.9 5.6 7.7 6.7

(14)

Table 4: Funding and expenditure at institutional level

* Funds for the programme Equilibrium, Expectations & Dynamics were added to the CeNDEF project. Exploitation of projects is only calculated at the termination of the project.

in € Budget Exploitation 1st flow of funds 2004 2004 RESAM 73001 WP Resam 2,039,987- 2,095,411-73002 Promovendi Resam 996,798- 707,706-73011 OBP Resam 411,920- 473,115-73036 Magazine 2,000-73037 Inaugural lectures 2,000-

3,286-73039 Bonus for Ph.D. students 2,000-

455-73040 Other costs 4,000-

6,387-73041 Tinbergen Research Institute 91,831- 103,812-73042 Tinbergen graduate school 113,000-

120,166-73043 Tinbergen Fellows 16,000-73044 Ph.D. networks 15,700- 15,599-73047 Organisation seminars 2,000- 1,182-73051 Scholar 15,000- 34,829 73056 Data collection 22,800- 24,716-73095 Income Resam 5,031,000 4,933,784 73099 Allocated to AgBS-RI 1,368,622- 1,368,624-Programme funding 2010031 Econometrics 10,800- 7,517 2010032 Operations Research 5,400- 579 2010033 Actuarial Sciences 3,375- 2,787-2010034 Transformation of Europe 12,825- 4,045 2010035 Methodology, History of Econ. 3,375- 1,180

2010036 Human Capital 14,175- 1,853

2010037 Experimental Political Econ. 11,475- 17,101-2010038 CeNDEF*

(15)

Box 2: Research highlight: Kees Jan van Garderen. Conditional Inference and Small Samples in Econometrics

For economists it is very natural to condition on economic variables, e.g. to condition on income when analysing expenditure. Regression functions, for example, are by definition conditional expectations and conditioning is fundamental in quantifying economic relations. The situation becomes more subtle, however, when income itself is regarded as a random variable

with a distribution depending on parameters. Conditioning then requires weak exogeneity of the explanatory variables and no feedback is allowed from expenditure back to income. Definitions of exogeneity can be put in terms of factorisations of the likelihood and valid conditioning depends on the mathematical structure of the model under investigation.

In applied economics we further condition to make statements about the accuracy of estimates. The accuracy depends on the sample available. When we have a small sample, with very little variation in e.g. income, than it is hard to estimate the effect of income on expenditure and the reported standard error should reflect this. In the linear regression model this leads to a reported variance of the estimator inversely proportional to the variance in the explanatory variables, σ2

(

X X

)

−1. This is a conditional expression given X, and calculated ex-post after the sample has been observed, and is not an ex-ante average over all possible values of X.

Our research program, which is sponsored by the KNAW and the FEE, is concerned with conditioning variables that are not necessarily economic in nature, but are exogenous and informative about the ex-post accuracy of estimation and inference. Ex-post because two realizations from an identical data generating process can contain very different information about the parameters, as with large and small samples or with widely spread versus highly concentrated incomes in the example above.

As a more interesting example consider the Purchasing Power Parity (PPP) hypothesis, which in its weak form implies that log real exchange rate between two countries must be stationary, even if log prices and the log nominal exchange rate are non-stationary. In a paper titled “Conditional Inference in the Cointegrated Vector Autoregressive Model” with Sophocles Mavroeidis1 we investigate equilibrium relationships between non-stationary variables and the speed of return to equilibrium. If the economic system is always in equilibrium, we cannot possibly estimate the speed of adjustment. The accuracy with which we can estimate the adjustment coefficient will thus depend on the variation around the equilibrium set. We cannot condition on this variation since the adjustment estimate is itself a function of this variation and this variation is not exogenous.

Our solution for an alternative conditioning statistic is based on the observation that the model is curved2. This implies, as we have shown in previous work, that (a) there are sensitive regions in the sample space (where Hessian of the likelihood is nearly singular) (b) there is an embedding model. This provides us with a mathematical structure that we can exploit by constructing a test of the maintained model against the embedding. In combination with an indicator of the sensitive region we define a new statistic that is nearly exogenous and indicative of the ex-post accuracy of the estimator. The inferential procedures we propose conditional on this statistic are much more reliable. For instance, unconditional confidence intervals can have a terrible coverage probability of 68% instead of claimed 95%, whereas our procedures almost have the correct coverage level, irrespective of the value of this statistics.

This is just one of many applications of general principles derived in the research program, which in this PPP example leads to valid inference even in cases where the return to equilibrium is very slow.

1 Sophocles was attracted from Oxford to the project as a postdoctoral research fellow. He recently took up a tenure track position at Brown

University in the US. We are about to appoint another postdoc. Cesar Ariza has recently joined as a PhD student and is working on likelihood based techniques for conditional inference.

2 There are many interesting intricacies and technicalities which we also investigate. The analysis of curved models requires non-standard

(non-Riemannian) geometry and various techniques based on exact finite sample theory and higher order asymptotic expansions can be expressed in differential geometrical terms.

(16)

CHAPTER 3: CURRENT STATE OF AFFAIRS

3.1. PROCESSES IN RESEARCH, INTERNAL AND EXTERNAL COLLABORATION

RESAM allocates resources, after evaluating past performance. RESAM stimulates and facilitates application for external funding (NWO, KNAW, EU). In general, the research institute tries to stimulate and active research environment, by a financing weekly general seminar, where participants from all Research Programmes meet, and it tries to assist Programme members, when necessary, by providing them with information and administrative support.

Actual research management takes place within the Research Programmes. Decisions on research strategies, research topics, joint work, participation in international networks , publication outlets are all taken within these Programmes, sometimes by the Programme director, but mostly in an informal way by direct communication and interaction within these groups. Research groups are typically small and interaction is frequent, direct and effective. RESAM basically monitors and controls by rewarding output.

Another way in which RESAM creates a stimulating research environment is by sponsoring and participating in the Tinbergen Institute (TI). Two other Dutch universities (Erasmus University and Free University) participate in the TI. It is their joint graduate school and facilitates exchange amongst its fellows (top researchers of the three participating faculties) by hosting (mostly weekly) seminar series (see box 3 for all RESAM seminars) and publishing a discussion paper series.

Box 3: Seminar series organised by and in co-operation with RESAM UvA-Econometrics Workshops

Organisation: Kees Jan van Garderen

TI Econometrics seminars

Organisation: Kees Jan van Garderen & Charles Bos

KAFEE Lunch Seminars

Organisation: Marcos Poplawski-Ribeiro, Valentin Panchenko & Erik Feijen

Amsterdam Research Group in History and Methodology of Economics Seminars

Organisation: Harro Maas

Economics Colloquia

Organisation: Franc Klaassen, Maurice Bun, Aljaž Ule & Florian Wagener

Tinbergen Labour Seminar Series

Organisation: Erik Plug, Bas van der Klaauw & Pieter Gautier

ENCORE Seminars and Workshops

Organisation: Jeroen Hinloopen

CREED-Tinbergen seminar series in Institution and Decision Analysis

Organisation: Arno Riedl

As a graduate school, the Tinbergen Institute, initiated some major changes in 2003. With the introduction of the Bachelor-Master structure in the Netherlands the TI has chosen to offer a two-year research master (Master of Philosophy in Economics). These two years are basically part of a five-year Ph.D. track. Up until last five-year most Dutch Ph.D. students started their work after four five-years of university education. The first year of our Ph.D. students’ four-year term usually consisted of additional courses at the Tinbergen Institute which left three years for actual research. The new master will be an integration of this ‘old first year’ together with the last ‘normal university year’. Instead of 4-4 track (which usually was a 4-1-3 track) there will now emerge a 3-2-3 system. The advantage of this system is that the new TI-master offers students an excellent research-oriented two-year programme with good opportunities to meet top-level supervisors (TI-fellows).

(17)

Recently an international peer review committee consisting of prof. Dale Jorgenson, prof. David Hendry, prof. Arie Kapteyn, prof. Robert Merton and prof. Torsten Persson judged that the level of instruction in the core courses is comparable to the first-year program in leading graduate schools in economics in the UK and North America.

The number of students starting a Ph.D. training within RESAM was very uneven in recent years (ten projects started in 2004 (four of these on external funding), two in 2003, 21 in 2002 and two in 2001). Probably only three projects will start in 2005. The jump from 2001 to 2002 was due to postponing entry as a result of a new system of financial support3. The strong drop in 2003 and 2004 was a

consequence of a financial crises and, since all projects run at least four years, because of the high number of projects started in 2002 that are still weighing down on the budget.

Table 5: Ph.D. graduations by cohort*

* Including all FEE Ph.D. students (also those now under the Amsterdam graduate Business School Research Institute)

As can be seen in table 5, on average, graduates needed 60 months from start of the contract to actual graduation. If a thesis is accepted by the supervisor, it easily takes four months until actual graduation (6 weeks for the committee to read and react, communication to the dean and the office of the pedel, time to print, etc). Adding queuing time for the auditorium, a lag of up to six months after the expiry date of the contract time is quite normal. Hence, average completion time of 60 months for the first 56%, compared to a formal minimum of some 54 months is not bad. Reason for real concern is the overall low percentage of graduations (56%). It is, however, expected that this figure will rise when the new Tinbergen-system, in which excellent master-students receive a comprehensive two-year research-training programme before entering the Ph.D., will have become operational.

In 2004 43 Ph.D. students were working on different projects at RESAM. Funding for six of these 43 projects were terminated. One student decided not to continue the Ph.D., five others are now finalizing their thesis. We expect them to graduate in 2005. Furthermore 10 new projects were initiated last year (five of them with external funding).

3.2. ACADEMIC REPUTATION

In 2003, CentER, the research institute in economics of Tilburg University, again drew up a ranking of Dutch economists and one of Dutch institutes and repeated this exercise in 2004. FEE ranked 3rd,

one place higher than the previous year, overtaking the VU. UvA also closed in on the EUR which occupies the second position. The number of FEE-researchers in the Top 40 also rose: nine FEE researchers (seven in 2003) were listed in the Top 40 of Dutch economists, CREEDs Peter Wakker taking the third position.

A ranking based on weighted publications exploits only one dimension of research performance. A ranking of European academic institutions in 19994, based on articles published in the ten most prestigious international journals from 1991 to 1996, has FEE ranking 17th. This puts FEE ahead of all other Dutch institutions: Tilburg (19), Maastricht (37), Erasmus (42), Groningen (55), Leiden (58), Nijmegen (81), Utrecht (97) and the Free University (111). Output is not scaled by size of the institute. The top ranking institution (LSE) has published almost 400 AER (American Economic

3 The ‘bursaal’-system was abolished in favor of the ‘AIO’-system. In the former system Ph.D. students are not employed by the unversity

but received a scholarship whereas in the latter system the Ph.D. students are employees with concommitant rights and legal positions.

4 P. Kalaitzidakis, T.P. Mamuneas & T. Stengos (1999). European economics: an analysis based on publications in the core journals,

European Economic Review, 43 (4-6), 1150-1168.

1992 1993 1994 1995 1996 1997 1998 1999 2000 Total/Average 24 11 13 13 13 16 16 15 13 134 15/24 9/11 11/13 7/13 8/13 11/16 6/16 6/15 1/13 74/134 0.63 0.82 0.85 0.54 0.62 0.69 0.38 0.40 0.08 56% 10/15 6/9 5/11 3/7 3/8 10/11 5/6 3/6 1/1 45/74 0.67 0.66 0.45 0.43 0.38 0.91 0.83 0.50 1.00 65% 66.1 66.3 63.6 66.6 60.3 54.0 55.5 56.3 55.0 60.41 Graduated within 60 months

Fraction graduated within 60 months Average duration to completion in months

Cohort

Projects started Graduated/Total

(18)

Review) equivalent pages, the top-ten all publish in excess of 140 AER equivalent pages. FEE published 86, Tilburg 80 pages, and all other Dutch institutions below 40 pages.

A ranking published in 2003, drawn up for the European Economic Association, puts the FEE at rank 10 in Europe. The ranking covers the period 1995-1999 and is based on thirty prestigious journals5.

Tilburg takes up rank 1 in Europe, Erasmus is at 15, VU at 30, , Maastricht at 31 and Groningen at 60. A ranking based on publication in some 650 journals in the period 1994-1998 puts UvA at rank 7 in Europe (Tilburg at 5, EUR at 8, VU at 19, Maastricht at 27 and Groningen at 29)6.

As table 6 indicates RESAM faculty members take up many positions as editors or associate editors of international journals. Membership of editorial boards is also frequent.

Table 6: Editorial Positions

5 P. Kalaitzidakis, T. Mamuneas & T. Stengos (2003). Rankings of economic journals and institutions in economics. Journal of the

European Economic Association, 1, (6), 1346-1366.

6 http://cwis.kub.nl/~few/few2/nieuws/Eurotop.htm

Name Editorship Journal Ranking IF

Bethlehem, J. Member editorial panel Journal of the Royal Statistics Society, Series A 1.068 Dhaene, J. Associate editor Insurance: Mathematics and Economics A 0.614 Ellman, M.J. Associate editor Cambridge Journal of Economics B 0.217

Ewijk, C. van Editor De Economist B 0.267

Goeree, J.K. Associate editor Games and Economic Behavior A 0.919 Gooijer, J.G. de Editor-in-chief International Journal of Forecasting B 0.598 Goovaerts, M.J. Editor Insurance: Mathematics and Economics A 0.614 Goovaerts, M.J. Editor Journal of Computational and Applied Mathematics B 0.567 Groot, W. Member editorial board Social Indicators Research A 0.398 Hartog, J. Member editorial board Economics of Education Review B 0.473

Hartog, J. Member editorial board Labour Economics B 0.409

Hinloopen, J. Co-editor Review of Industrial Organization B 0.307

Hommes, C. Associate editor Computational Economics B

Hommes, C. Editor Journal of Economic Dynamics and Control A 0.690

Hommes, C. Associate editor Macroeconomic Dynamics B 0.729

Hommes, C. Associate editor Nonlinear Science 1.615

Hommes, C. Associate editor Quantitative Finance B

Kaas, R. Managing editor Insurance: Mathematics and Economics A 0.614

Kleibergen, F.R. Advisory editor Economics Letters B 0.337

Kuiper, E. Associate editor Feminist Economics B 0.250

Morgan, M.S. Member editorial board History of Political Economy A 0.142 Oosterbeek, H. Member editorial board Economics of Education Review B 0.473 Praag, C.M. van Associate editor Small Business Economics B 0.534

Schram, A. Editor Experimental Economics B

Sonnemans, J. Member editorial board Quantitative Finance B

Sonnemans, J. Member editorial board Journal of Economic Psychology B 0.750

Theeuwes, J. Member editorial board Labour Economics B 0.409

Tuinstra, J. Associate editor Journal of Economic Dynamics and Control A 0.690 Volgenant, A. Advisory editor Computers and Operations Research B 0.486 Wakker, P.P. Member editorial board Journal of Behavioral Decision Making 1.093 Wakker, P.P. Member editorial board Journal of Risk and Uncertainty A 0.759 Wakker, P.P. Member editorial board Medical Decision Making B 1.718

Wakker, P.P. Member editorial board Management Science A 1.468

Wakker, P.P. Member editorial board Theory and Decision 0.149

Winden, F.A.A.M. van Member editorial board European Journal of Political Economy B

Winden, F.A.A.M. van Member editorial board Public Choice B 0.297 Wolthuis, H. Associate editor Insurance: Mathematics and Economics A 0.614

(19)

3.3. OVERVIEW OF RESULTS

Figure 2: Number of publication 1996-2004

A: A-publications, B: B-publications, C: C-publications, B/R: Books and reports, ONB: Unknown (not ranked)

Figure 2 shows a slow but steady increase in the number of A publications during 1996-2002 and a slight decrease in the last two years. 7 We should note however, that the ranking of publications is not

constant over time. A systematic re-evaluation of journal rankings was first applied to the publications of the year 2000. Due to this re-evaluation the number of unknown (ONB) publication has been reduced to zero. The reduction in 2004 is due to the application of stricter rules for admitting unranked journals to the RESAM list.

Note also that as of 2002 publications refer to RESAM only whereas before they included the output of the research programmes of the AgBS-RI (Amsterdam graduate Business School-Research Institute).

Table 7: Aggregated results of the institute

8

Output in different outlets by research programme is shown in table 7.

7 Due to a miscalculation the number of publications in the year 1999 (as published in the Annual Report 1999 and the Annual Report 2000)

was much too high (for 1999 41 A, 70 B, 80 C, 72 B/R and 2 ONB were given). The figures and tables in this report (as well as those in the Annual Report 2001) show the correct numbers for all years.

8 As of last year, only publications of faculty on which their UvA-affilition is mentioned, will be counted in the tables and figures. The total

number of Academic Publications (books) includes monographs as well as chapters in books. In 2004 one monographs was published by an A-level publisher and two by non-refereed publishers. Publications in proceedings are counted in the Academic Publications (excl. books) section. 0 10 20 30 40 50 60 70 80 1996 1997 1998 1999 2000 2001 2002 RESAM 2003 RESAM 2004 RESAM A B C B/R ONB

METIS code Research programme

Ac.nonref (ex. books) Ac.nonref (books) Working & Discussion Papers Prof. publ. Pop. publ. Ph.D. Theses Fte wp1 excl. Ph.D.'s A B C A B C

RES - EEM UvA-Econometrics 3 7 2 - - - 3 - 18 1 - - 3.35

RES - OON Operations Research 1 4 1 - - - 1 - 11 1 2 - 2.45

RES - E&D Equilibrium, Expectations and Dynamics - 6 2 - 3 - 2 2 11 - 2 - 2.50

RES - ACT Actuarial Science 4 10 3 4 - - 16 1 16 9 - - 0.88

RES - TOE Transformation of Europe 2 8 3 2 1 - 8 2 23 9 1 - 3.97

RES - HUM Human Capital 6 12 3 1 7 1 9 9 45 22 21 2 4.27

RES - HME Methodology & History of Economics 1 6 6 3 8 1 6 7 6 3 2 - 1.70 RES - EXP Experimental & Political Economics 6 6 2 1 1 - - - 22 - - - 3.11

SEO - SEO SEO-Amsterdam Economics 2 5 2 1 1 1 59 15 11 6 4 1 0.00

RES-OVO Other Research KE - - - 0.43

RES - OVO Other Research AE - - - 1 - - - 1 0.09

Total 23 59 23 12 21 4 103 36 163 51 30 4 22.75 Aggregated total 105 37 103 36 158 51 30 4 22.75 Ac.ref (excl. books) Ac.ref (books)

(20)

Figure 3: RESAM dissertations*

* From 2002 excluding dissertations within programmes that are now under AgBS-RI. Category I : Ph.D. students who worked at FEE and graduated at FEE, II: external candidates who graduated at FEE, III: FEE staff that graduated elsewhere, IV: non-FEE student who graduated elsewhere with an FEE promotor.

The number of dissertations has dropped to six in 2003 and four in 2004. This was mainly due to the fact that rather many dissertations were successfully defended in 2001 and 2002. As the hiring rate fluctuated over the years, contract expirations are also very uneven. It again has to be noted here that as of 2002 dissertations refer to RESAM only whereas before they included the output of the research programmes of the research institute of the AgBS. It is expected that numbers will again start to increase in 2005. 0 5 1 0 1 5 2 0 2 5 3 0 3 5 1 9 9 2 1 9 9 3 1 9 9 4 1 9 9 5 1 9 9 6 1 9 9 7 1 9 9 8 1 9 9 9 2 0 0 0 2 0 0 1 2 0 0 2 2 0 0 3 2 0 0 4 IV III II I

(21)

CHAPTER 4: ANALYSIS, PERSPECTIVES AND EXPECTATIONS

FOR THE INSTITUTE

4.1. SWOT DIRECTOR RESAM

The major strength of the research institute is the general outlook and orientation of faculty members. There is very active, lively research climate, with high ambitions and much interaction and exchange. Both in quantity and in quality, publications are at high level. The Jorgenson-committee recently evaluated the Tinbergen Institute very positively as research institute and graduate school. Faculty members perform well in searching external funding from national (NWO, KNAW) and international (EU) sources.

Still, there are weaknesses. Success in obtaining external funding is not equally distributed among Research Programmes. Publications are in some cases, unevenly distributed within Programmes, and there is scope for raising the bottom of this distribution.

The recent development of a strong Mphil programme by the Tinbergen Institute provides an excellent opportunity to raise the proportion of Ph.D. students that finish their thesis within the standard time. It is important to utilize this opportunity and to support the new programme fully both financially and in terms of teaching capacity.

But certainly there are threats and hurdles. RESAM Research Programmes have gained international reputation, but without significant funding to provide excellent research opportunities further growth will not be possible, and deterioration may set in. The increased openness of the international research community and increased mobility of faculty generates a more competitive labour market, and attracting and keeping highly qualified faculty is not easy. This was true in 2004 and even more so in 2005.

Given the ambitions, opportunities and threats, RESAM sees no reason for changes in its objectives an research strategy. RESAM’s general strategy seems to work quite well, with specific minimum research output standards at the individual level, general measures to enhance an active, ambitious research climate, discussion of goals and performances with individual Programme Directors to discuss common concerns and to share the responsibility for good collective performance.

4.2. ASSESSMENT OF THE COUNCIL OF PROGRAMME LEADERS

Overall, the Council has reason to be quite satisfied with the results obtained over the last couple of years including 2004. The number of A and B-level publications was slightly lower than in 2003 but overall output was satisfactorily both in quality and quantity. Again a large number of FEE-researchers made it into the 2004 edition of the Tilburg Top 40 of Dutch economists. Most of the research groups have also proven to be viable and are highly active in research, as is shown by the fact that many seminar series have been organised, which provide valuable opportunities for exchange and interaction. If we continue this trend, we will undoubtedly remain one of the major European universities as far as research is concerned. The clear objectives set and the consistent faculty-policy concerning quality of research have certainly contributed much to these results. Furthermore, the atmosphere is good and a general positive and enthusiastic outlook can be detected.

There are, however, also points of concern. First and foremost is personnel policy. As has been shown above, the Faculty is on the right track in creating a top-level research institute in economics and econometrics but efforts will need to be continued to remain on this track. Last year the Council noted that the departure of one or two top-level researchers would prove to be a serious danger to the FEE’s ambition. Since then three prominent researchers have left the FEE (Claessens, Goeree and Wakker). Although it seems clear that their departure couldn’t be prevented by any FEE policy it will prove to

(22)

be a serious blow for the FEE. The faculty needs to attract new top-level researchers and further improve its research environment so that good researchers feel welcome, are able to realize their full potential and FEE remains visible as one of the leading research institutes in Europe.

Secondly is the current financial constraint under which the faculty has to operate. There are too few funds for basic necessities such as for conference visits, inviting guests, conducting experiments or buying data.

Finally the Council is divided about the developments at the Tinbergen Institute. Not all fields in which research is done by RESAM programmes are represented in the TI, notably statistics and actuarial science. This also has implications for the TI as a graduate school. The TI programme is not suited for all RESAM-students and might prove to be holding back the progress of Ph.D.’s with projects in specific fields. On the other hand, creating a small pool of excellent mphil-students from which Ph.D.’s can be selected is seen as a positive development. The RESAM-director, also a member of the TI Admission Board, will have to see to it that Ph.D. students are evenly distributed among research programmes.

B ox 4: After six years professor Joop Hartog resigns as director RESAM

As of January 1 2005, Joop Hartog has resigned his post as director of the research institute RESAM. The institute was established in 1998 after the enactment of the new law on modernizing university governance, MUB (Modernisering Universitair Bestuur). Joop Hartog became the institute’s first director and was responsible for building it from the ground up. He succeeded in creating a small-staffed and flexible unit capable of decisive action.

Under his leadership the number of research programmes was reduced and top-level research has been stimulated. Without doubt, these efforts contributed to the good VSNU assessment in 2002. Three of the (then) thirteen research programmes were given an ‘excellent’-rating for scientific quality. The programmes that the assessment-committee deemed to perform unsatisfactory have in the mean time

been terminated. An important instrument he created to improve the quality of research is the transparent RESAM-system of weighing research output and allocating research time.

Joop Hartog, furthermore, gave researchers a strong impetus to submit research proposals in order to attract external funding for research. FEE has been quite successful in securing external funding over the last years and two major (VENI) subsidies have recently been awarded to two young FEE economists. In co-operation with the UvA liaison office, RESAM did research on what research programmes are be best suited to be apply for which (EU) subsidies and administrative assistance has been expanded. Furthermore, an easy-to-use website was created to give researchers information on interesting possibilities for research-funding.

We are very happy his qualities will not be lost to the FEE: in the coming years Joop Hartog will again be able to fully dedicate himself to research and teaching. FEE wishes to thank him for six successful years as RESAM director and his successor is indebted to him for leaving behind a smoothly running institute.

(23)

B

(24)
(25)

UvA-Econometrics – Kiviet Quantitative Economics

UvA-Econometrics

Programme director:

Prof. dr J.F. Kiviet

Department:

Quantitative

Economics

(KE)

METIS-code:

uva/fee/res/eem/prog

JEL-classification:

C

Web-address: www.fee.uva.nl/ke/UvA-Econometrics

VSNU-scores 1995-2000: Quality: 5, Productivity: 3, Relevance: 3, Viability: 4

Members of the research group and research in FTEs

9

Programme design

Objectives

Assessment and enhancement of the accuracy, efficiency and robustness of econometric inference obtained from finite sets of empirical data by models which may be dynamic, non-linear, not fully parametric, and nonetheless misspecified. Separate attention is being paid to cases where the data are

9 The numbers in the columns represent the research-time earned with publications under the RESAM-system. Name Title Function

Total 2002 Total 2003 Total 2004 Dept. Funding

Arisa Rojas, C. msc aio - - 0.20 KE 1

Bethlehem, J.G prof dr hgl 0.11 0.11 0.11 KE 1

Boswijk, H.P prof dr hgl 0.50 0.50 0.50 KE 1

Bun, M. dr ud 0.50 0.50 0.50 KE 1

Cheng, Y. msc aio 0.05 0.60 0.60 KE 1

Cramer, J.S. prof dr em. - - - KE pm

Garderen, K.J. van dr uhd 0.80 0.80 0.80 KE 2

Giersbergen, N.P.A. van dr ud 0.48 0.48 0.24 KE 1

Gooijer, J.G. de prof dr hgl 0.50 0.50 0.50 KE 1 Joseph, A. drs aio 0.20 0.60 0.20 KE 1 Kiviet, J.F. prof dr hgl 0.50 0.50 0.50 KE 1 Kleibergen, F.R. dr uhd 0.80 0.55 0.00 KE 2 Klein, A.A.B. dr ud 0.50 0.50 0.50 KE 1 Mavroeidis, S. dr postdoc 0.20 0.80 0.60 KE 1 Niemczyk, J. msc aio - - 0.10 KE 1 Omtzigt, P.H. dr postdoc 0.15 0.45 0.10 KE 2

Ophem, J.C.M. van dr uhd 0.20 0.00 0.50 KE 1

Ploeg, A. van der drs burs 0.60 0.60 0.40 KE 1

Ploeg, A. van der drs postdoc - - 0.27 KE 1

Zerom, D. drs burs 0.30 - - KE 1

Total 1st flow of funds 4.88 5.94 5.72

Total 2nd flow of funds 1.75 1.80 0.90

Total 3rd flow of funds 0.00 0.00 0.00

Total 1st f.o.f. excl. Ph.D.'s 3.73 4.14 3.35

Total 1st-3rd flow of funds 6.63 7.74 6.62

(26)

discrete or truncated, stationary or nonstationary, trended and/or seasonal, and where they pertain to a cross-section, a set of discrete time-series, or a panel.

Motivation

Empirical economic data are usually not obtained from markets or agents in static equilibrium, but they give a random and disturbed indication at a certain moment in time, or over a relatively short period, of a dynamic adjustment process. Also they usually concern just a few aspects of the underlying mostly very complex linear or non-linear economic system, and sample sizes are often rather small. The various projects united in this programme all try to gear statistical techniques to the typical characteristics of particular relevant empirical economic relationships and corresponding observed data in the interest of accurate and efficient inference. The goal is to obtain a proper interpretation of the essentials of the analysed phenomena in order to test economic theory, to support decision making and for forecasting purposes.

Techniques

Both analytic and experimental methods are used in this programme to improve understanding of the available econometric or statistical inference techniques, and to develop and test alternatives. The analytic aspects often involve the derivation (possibly using computer algebra systems) of asymptotic distributions, the approximation of finite sample moments or distribution functions, the elimination of nuisance parameters etc. In computer simulations of completely specified systems the existing standard procedures and the newly developed techniques are then compared and evaluated experimentally. Occasionally the alternative techniques as such are of an experimental nature, because they involve computer-intensive methods (bootstrap resampling, randomization techniques, simulation-based inference). Actual data often serve to illustrate the empirical relevance and practical usefulness of the theoretical findings, but at times empirical issues are the prime motivation of the research projects engaged in.

Applications

The fundamental problems of econometrics indicated above are studied in an interplay with actual applied econometric research. These applications come from both macro and micro economics or business and finance. Aggregate demand (the consumption function) but also demand systems, monetary relationships (demand for money, interest rates) but also data from financial markets (stock returns, credit risk) are studied or provide prototypical examples for exercises in econometric theory on modelling and analysing dynamic relationships, focusing on various aspects such as dynamic or functional misspecification, order of integration, cointegration, exogeneity, seasonality, structural change in parameter values, stochastic volatility, approximation errors in inference due to finite sample sizes, etc. The economic behaviour of individual agents is analysed on the basis of cross-section data (wage determination, job mobility and allocation), duration data (on unemployment) and panel and longitudinal data (budget survey analysis, analysis of treatment effect such as training).

Subprogrammes, themes

The programme is not a collection of separate clearly demarcated sub-programmes, though within the general theme described above, the following six partly intertwined sub-themes can be distinguished. The first theme is primarily concerned with accurate inference in finite samples. Within this theme, analytical finite sample approximations, Bayesian inference, simulation-based inference, inference based on GMM, conditional inference, and methods from differential geometry are studied for (and applied in) models that may be dynamic, simultaneous, non-linear or non-standard in another way. Main contributors are Kiviet, van Garderen, Kleibergen, van Giersbergen and Bun.

The second theme centers around the analysis of non-stationary data. This leads to the analysis of unit roots, cointegration and error correction models, the role of (weak) exogeneity in such models, the development of robust two-step procedures, the analysis of non-stationary seasonal and periodic models, and non-stationary models for processes in finance and marketing. The main participants are Boswijk, Kleibergen, van Giersbergen and Omtzigt.

(27)

UvA-Econometrics – Kiviet Quantitative Economics

The third theme deals with model selection and model comparison. Within this theme, both linear and non-linear models are considered, nested or non-nested, with an emphasis on time series. Relevant topics are information criteria and entropy measures, the Fisher information matrix, model inference, and space-time modeling of socio-economic data. Contributors are de Gooijer, Bethlehem, Kleibergen, Klein and Cheng.

In the fourth theme the focus is on the econometrics of financial markets. Topics are ARCH and stochastic volatility models, the econometrics of the CAPM and factor models, econometric analysis of credit risk, and the analysis of option data and implied volatilities. Participants are here Boswijk, Kleibergen and van der Ploeg.

The fifth theme is concerned with micro-econometrics, focusing on limited dependent and discrete data, with applications in labor market econometrics. Contributors are van Ophem and Cramer. Finally there are miscellanea, including work on poverty measures by van Garderen and on historical aspects of statistics and econometrics by Kiviet.

Resources and funding

Until a few years back the budget for compensating travel, subsistance and conference fees of the research group was very tight. Strict rationing of the budget over the active researchers induced most of them to find alternative funding (for instance from budgets created in the past on the basis of successful PhD defences, from compensations paid by the business school for special courses taught, or originating from other commissioners of special projects, etc.). As a result last years budget obtained via RESAM was hardly used. Since it is expected that most of the alternative funds will be exhausted soon, UvA-Econometrics hopes that the level of the present annual budget can be maintained. Over the last few years researchers have been confronted with sharply increasing price levels at conferences and for travel and accommodation.

Programme evaluation

The current achievements within this program are still much in line with the latest VSNU assessment covering 1996 through 2000, which awarded an excellent mark for quality, a good mark regarding viability, and satisfactory marks with respect to relevance and productivity, where the latter was mainly due to the relatively small number of Ph.D. students.

During 2004 a considerable number of papers has been published in leading journals, and also the number of papers not yet published though already accepted by prominent periodicals is quite substantial. These achievements have been obtained in all sub-themes of the UvA-Econometrics research program and perpetuate its reputation regarding quality and productivity of research output. The program has been able to extend its number of Ph.D. students, but the number is still too low. Attempts are being made to acquire NWO funding for extra positions, and to stimulate talented external candidates from underdeveloped countries to apply for Ph.D. fellowships at NUFFIC, but at this stage no successes can be mentioned yet. Such successes seem indispensable to improve the program's reputation regarding overall productivity and viability.

Substantial labour-investments have been undertaken over the last year, and will be undertaken during the next year, to obtain EU-funding (jointly with EU partners) for projects that aim at human capacity building regarding research skills in (applied) econometrics at particular Asian universities. Hopefully, this will enable to extend the UvA-Econometrics activities in this new and challenging direction from next year on. Such activities could also have a noticeable effect on the UvA-Econometrics research agenda (in an applied direction) and thus enhance its relevance and viability.

(28)

The current size of the group of researchers in econometrics offers just the minimal critical mass required to maintain a very stimulating research environment. Almost weekly a Friday afternoon (external) seminar or (internal) workshop is organized, usually at the Tinbergen Institute. All members, especially the Ph.D. students (which are presently all from abroad), are strongly encouraged to participate actively in these weekly joint exchanges of ideas and achievements. All activities and achievements of UvA-Econometrics are communicated via its web-site www.fee.uva.nl/ke/UvA-Econometrics from which UvA-Econometrics discussion papers can be downloaded.

It is worrying, that some of the allocated research input for 2004 has actually not been consumed (made productive), because claims from faculty management obstructed the planned research activities by particular individuals. The Faculty's Dean will be urged to compensate these losses. Most members of UvA-Econometrics continue to operate in intensive formal and informal national and international networks. It is the ambition of UvA-Econometrics to find further international recognition as one of the major strongholds in theoretical econometrics worldwide. The activities and achievements over 2004 (number and quality of publications, presentations at and invitations for international meetings, editorial responsibilities, hosting of visiting scholars, exposure at peer institutions) have been very substantial, but certainly leave ample room for further qualitative and quantitative improvements.

Key publications

Boswijk, H.P. & Lucas, A. (2002). Semi-nonparametric cointegration testing. Journal of Econometrics, 108, 253-280.

Garderen, K.J. van (2001). Optimal prediction in loglinear models. Journal of Econometrics, 104, 119-140.

Giersbergen, N.P.A. van & Kiviet, J.F. (2002). How to implement the bootstrap in static or stable dynamic regression models. Journal of Econometrics, 108, 133-156.

Gooijer, J.G. de & Zerom, D. (2003). On additive conditional quantiles with high-dimensional covariates. Journal of the American Statistical Association, 98, 135-146.

Kleibergen, F. (2002). Pivotal statistics for testing structural parameters in instrumental variables regression. Econometrica, 70, 1781-1804

Klein, A. & Spreij, P. (2001). On Stein's equation, Vandermonde matrices and Fisher's information matrix of time series processes. Part I: The autoregressive moving average process. Linear Algebra and its Applications, 329, 9-47.

Leuven, E., Oosterbeek, H. & Ophem, J.C.M. van (2004). Explaining international differences in male skill wage differentials by differences in demand and supply of skill. The Economic Journal,

114, 466-486.

Forthcoming publications

Boswijk, H.P. & Doornik, J.A. (2005). Distribution approximations for cointegration tests with stationary exogenous regressors. Accepted for publication in Journal of Applied Econometrics.

Boswijk, H.P. & Franses, P.H. (2005). On the econometrics of the Bass diffusion model. Accepted for publication in Journal of Business & Economic Statistics.

Boswijk, H.P. & Franses, P.H. (2005). Robust inference on average economic growth. Accepted for publication in Oxford Bulletin of Economics and Statistics.

Bun, M.J.G. & Carree, M.A. (2005). Bias-corrected Estimation in Dynamic Panel Data Models. Accepted for publication in Journal of Business and Economic Statistics.

Bun, M.J.G. & Kiviet, J.F. (2005). The Effects of Dynamic Feedbacks on LS and MM Estimator Accuracy in Panel Data Models. Accepted for publication in Journal of Econometrics.

(29)

UvA-Econometrics – Kiviet Quantitative Economics

Cubadda, G. & Omtzigt, P. (2005). Small-sample improvements in the statistical analysis of seasonally cointegrated systems. Journal of Computational Statistics and Data Analysis, 49, 333-348.

Joseph, A.S. & Kiviet, J.F. (2005). Viewing the relative efficiency of IV estimators in models with lagged and instantaneous feedbacks. Journal of Computational Statistics and Data Analysis,

49, 417-444.

Kiviet, J.F. & Phillips, G.D.A. (2005). Moment approximation for least squares estimators in dynamic regression models with a unit root. Accepted for publication in The Econometrics Journal. Klein, A. & Spreij, P. (2005). On the solution of Stein’s equation and Fisher’s information matrix of

an ARMAX process. Accepted for publication in Linear Algebra and its Applications.

Mavroeidis, S. (2005). Identification issues in Forward-Looking models estimated by GMM with an application to the Phillips Curve. Accepted for publication in Journal of Money Credit and Banking.

Omtzigt, P. & Paruolo, P. (2005). Impact factors. Accepted for publication in Journal of Econometrics.

Publications in numbers

Academic publications (excluding publications in/of books) – refereed

A Kleibergen, F. (2004). Testing Subsets of Structural Parameters in the IV Regression Model. Review of Economics and Statistics, 86, (1), 418-423. [A]

Kleibergen, F. (2004). Invariant Bayesian Inference in Regression Models that is robust against the Jeffreys-Lindleys Paradox. Journal of Econometrics,123, 227-258. [A].

Leuven, E., Oosterbeek, H. & Ophem, J.C.M. van (2004). Explaining international differences in male skill wage differentials by differences in demand and supply of skill. The Economic Journal,

114, 466-486. [A].

B Boswijk, H.P. & Doornik, J.A. (2004). Identifying, estimating and testing restricted cointegrated systems: An overview. Statistica Neerlandica, 58, 440-465. [B].

Bun, M.J.G. (2004). Testing poolability in a system of dynamic regressions with nonspherical disturbances. Empirical Economics, 29, (1), 89-106. [B].

UvA-Econometrics 2004

1) Academic publications a) in refereed journals A 3

B 7 C 2 b) in other journals 2 c) book chapters A -B -C -Other -d) in proceedings 1 Total 15 2) Monographs A -B -C -3) Ph.D. theses -4) Professional publications 1 5) Popular publications -6) Working papers 18 Total 34 12

Figure

Updating...

References

Related subjects :